Metraipolis › archive › dc_49eeff0b953a
DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA — arXiv:2608.28108
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28108
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:33:23.625Z
- SHA-256 of the archived text
03a6207c331c2cc5ea571114ef7c08960088462bf2f4cdc23cc7aaa82339c683- Stable URL of this page
https://metraipolis.com/documento/dc_49eeff0b953a
How to cite
DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA — arXiv:2608.28108 — arXiv (en), https://arxiv.org/abs/2608.28108 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49eeff0b953a (Metraipolis archive dc_49eeff0b953a, sha256 03a6207c331c2cc5ea571114ef7c08960088462bf2f4cdc23cc7aaa82339c683)
BibTeX
@misc{dc49eeff0b953a,
title = {DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA — arXiv:2608.28108},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28108},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49eeff0b953a; sha256 03a6207c331c2cc5ea571114ef7c08960088462bf2f4cdc23cc7aaa82339c683},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28108. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action models (VLAs) allow users to specify manipulation tasks in natural language, but distinguishing a target or placement goal among objects of the same category or similar appearance requires detailed expressions that VLAs may not use reliably. We propose DeicticVLA, which canonicalizes Language Instruction (LI), Vision-Language Instruction (VLI), and Visual Instruction (VI) into a text prompt and deictic masks through text-prompt completion and deictic gesture grounding, enabling a single pretrained VLA to handle all three instruction modes. With a shared backbone, demonstrations, and matched training steps, we compare two RGB visual prompting methods, two separate-channel mask prompting methods, and three training strategies in simulation. Under two-stage training, the four prompting methods achieve high in-distribution success but differ in their ability to use deictic masks in unseen layouts. Across methods, training-strategy ablations show that two-stage training improves such use, while retaining second-stage LI data mitigates forgetting without reducing VLI and VI performance. In three real-world tasks, one policy supports all modes. VLI and VI outperform LI under unseen expressions, appearance changes, and novel objects. For unseen categories, both achieve 100% success, compared with 16.7% for jointly trained LI. These results demonstrate the unified three-mode interface and guide DeicticVLA design. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28108 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T11:10:05.348Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).